Towards Real-time High-Definition Image Snow Removal: Efficient Pyramid Network with Asymmetrical Encoder-decoder Architecture

TL;DR

This paper introduces an efficient pyramid network with an asymmetrical encoder-decoder architecture designed for real-time high-definition image desnowing, effectively handling complex snowy degradation and outperforming existing methods in both quality and speed.

Contribution

The paper proposes a novel network architecture that improves the complexity-performance trade-off for real-time HD image desnowing, especially under complex snowy conditions.

Findings

Outperforms state-of-the-art methods in PSNR on multiple datasets.

Achieves better complexity-performance balance for HD and Ultra-HD images.

Significantly improves image quality metrics in extensive experiments.

Abstract

In winter scenes, the degradation of images taken under snow can be pretty complex, where the spatial distribution of snowy degradation is varied from image to image. Recent methods adopt deep neural networks to directly recover clean scenes from snowy images. However, due to the paradox caused by the variation of complex snowy degradation, achieving reliable High-Definition image desnowing performance in real time is a considerable challenge. We develop a novel Efficient Pyramid Network with asymmetrical encoder-decoder architecture for real-time HD image desnowing. The general idea of our proposed network is to utilize the multi-scale feature flow fully and implicitly mine clean cues from features. Compared with previous state-of-the-art desnowing methods, our approach achieves a better complexity-performance trade-off and effectively handles the processing difficulties of HD and Ultra-HD images. The extensive experiments on three large-scale image desnowing datasets demonstrate that our method surpasses all state-of-the-art approaches by a large margin both quantitatively and qualitatively, boosting the PSNR metric from 31.76 dB to 34.10 dB on the CSD test dataset and from 28.29 dB to 30.87 dB on the SRRS test dataset.